Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 10993
    Prev
    Next
    INDEX
    Explanations

    verbs related to creating, establishing, and building

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of forging or creating connections, agreements, or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    psc
    -0.75
    imation
    -0.68
    BUS
    -0.68
    TRY
    -0.63
    mins
    -0.63
    posing
    -0.61
    engu
    -0.61
     Mub
    -0.59
    enhagen
    -0.59
    ocating
    -0.59
    POSITIVE LOGITS
     alliances
    0.99
    smanship
    0.89
     anew
    0.89
     friendships
    0.80
     partnerships
    0.77
    ress
    0.75
    resses
    0.73
     elaborate
    0.73
     lasting
    0.73
     relationships
    0.73
    Activations Density 0.093%

    No Known Activations